paper-writing-section
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and refine content from external files like .tex documents and experiment logs, which creates a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: Step 1 in SKILL.md specifies reading existing paper files and context documents.
- Boundary markers: The skill does not explicitly utilize specific delimiters or instructions to ignore embedded commands within the ingested project files.
- Capability inventory: The skill possesses the ability to read local filesystem content and generate LaTeX text based on that content.
- Sanitization: No specific filtering or sanitization of input data is defined in the workflow or reference prompts.
Audit Metadata